mudler

mudler/vllm.cpp

a community oriented 1:1, vLLM-alike (Continuous batching, paged KV) engine in C++ with additional features (GGUF, RadixAttention, Cache-aware scheduling, ...)

⭐ 318 ⑂ 46 C++ Apache-2.0 · 7 小时前推送
318
Watchers
0
贡献者
0
Commits
0
Releases
546
Open Issues
7 小时前
最近推送
原文 中文
暂无 README